YOLOv8 vs RetinaNet vs EfficientDet: A Comparative Analysis for Modern Object Detection
Object detection plays a vital role in computer vision. It facilitates machines to comprehend and interpret images and videos and make decisions based on visual statistics. The search for the finest object detection algorithm continues to be an important endeavour in the area of computer vision. For...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Swedish College of Egineering and Technology
2025-02-01
|
| Series: | International Journal of Emerging Engineering and Technology |
| Subjects: | |
| Online Access: | https://grsh.org/journal1/index.php/ijeet/article/view/35 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Object detection plays a vital role in computer vision. It facilitates machines to comprehend and interpret images and videos and make decisions based on visual statistics. The search for the finest object detection algorithm continues to be an important endeavour in the area of computer vision. For this purpose, this paper includes three leading models—YOLO (You Only Look Once), RetinaNet, and EfficientDet, which are thoroughly examined and analyzed for object detection. We compare these three algorithms using the COCO dataset, which mainly comprises three categories of data, which are discussed in this paper. These techniques were examined using evaluation metrics. It helps to assess which algorithm is better for object detection. For this study, we used many AI-based libraries available in Python. |
|---|---|
| ISSN: | 2958-3764 |